To mitigate the extrapolation error arising from offline reinforcement learning (RL) paradigm,
existing methods typically make learned-functions over-conservative or enforce global policy …

Offline reinforcement learning (RL) seeks to learn optimal policies from static datasets
without interacting with the environment. A common challenge is handling multi-modal …

Offline reinforcement learning (RL) methodologies enforce constraints on the policy to
adhere closely to the behavior policy, thereby stabilizing value learning and mitigating the …